Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3315 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2922. Min Range: -1.2922

Max Act: 1.2922. Min Act: -0.0000

Data Index: 1138226 (C4 (Web Text))

Max Activating Token Index: 174

Text #1

Max Range: 1.2922. Min Range: -1.2922

Max Act: 1.0555. Min Act: -0.0000

Data Index: 1288280 (C4 (Web Text))

Max Activating Token Index: 550

Text #2

Max Range: 1.2922. Min Range: -1.2922

Max Act: 1.0358. Min Act: -0.0000

Data Index: 556574 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 1.2922. Min Range: -1.2922

Max Act: 1.0200. Min Act: -0.0000

Data Index: 1060148 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 1.2922. Min Range: -1.2922

Max Act: 1.0059. Min Act: -0.0000

Data Index: 181008 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 1.2922. Min Range: -1.2922

Max Act: 0.9917. Min Act: -0.0000

Data Index: 389636 (C4 (Web Text))

Max Activating Token Index: 584

Text #6

Max Range: 1.2922. Min Range: -1.2922

Max Act: 0.9642. Min Act: -0.0000

Data Index: 608159 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 1.2922. Min Range: -1.2922

Max Act: 0.9394. Min Act: -0.0000

Data Index: 683598 (C4 (Web Text))

Max Activating Token Index: 759

Text #8

Max Range: 1.2922. Min Range: -1.2922

Max Act: 0.8907. Min Act: -0.0000

Data Index: 1159546 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 1.2922. Min Range: -1.2922

Max Act: 0.8879. Min Act: -0.0000

Data Index: 1086368 (C4 (Web Text))

Max Activating Token Index: 890

Text #10

Max Range: 1.2922. Min Range: -1.2922

Max Act: 0.9133. Min Act: -0.0000

Data Index: 910250 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 1.2922. Min Range: -1.2922

Max Act: 0.8789. Min Act: -0.0000

Data Index: 16301 (C4 (Web Text))

Max Activating Token Index: 989

Text #12

Max Range: 1.2922. Min Range: -1.2922

Max Act: 0.9042. Min Act: -0.0000

Data Index: 304928 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 1.2922. Min Range: -1.2922

Max Act: 0.8924. Min Act: -0.0000

Data Index: 375133 (C4 (Web Text))

Max Activating Token Index: 397

Text #14

Max Range: 1.2922. Min Range: -1.2922

Max Act: 0.9472. Min Act: -0.0000

Data Index: 337650 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 1.2922. Min Range: -1.2922

Max Act: 0.9092. Min Act: -0.0000

Data Index: 122154 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 1.2922. Min Range: -1.2922

Max Act: 0.9226. Min Act: -0.0000

Data Index: 756966 (C4 (Web Text))

Max Activating Token Index: 584

Text #17

Max Range: 1.2922. Min Range: -1.2922

Max Act: 0.8595. Min Act: -0.0000

Data Index: 624828 (C4 (Web Text))

Max Activating Token Index: 983

Text #18

Max Range: 1.2922. Min Range: -1.2922

Max Act: 0.8347. Min Act: -0.0000

Data Index: 655455 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 1.2922. Min Range: -1.2922

Max Act: 0.8507. Min Act: -0.0000

Data Index: 545252 (C4 (Web Text))

Max Activating Token Index: 872